Borrowing it
Nothing to install: this file belongs to RorroRojas3/awesome-claude-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RorroRojas3/awesome-claude-copilot/main/.claude/agents/github-actions-reviewer.mdgit clone --depth 1 https://github.com/RorroRojas3/awesome-claude-copilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/rorrorojas3/awesome-claude-copilot/github-actions-reviewer)<a href="https://agentmods.dev/agents/rorrorojas3/awesome-claude-copilot/github-actions-reviewer"><img src="https://agentmods.dev/badge/agents/rorrorojas3/awesome-claude-copilot/github-actions-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/rorrorojas3/awesome-claude-copilot/github-actions-reviewer"><img src="https://agentmods.dev/badge/agents/rorrorojas3/awesome-claude-copilot/github-actions-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.01230 |
| Opus 5.5 | $0.00037 | $0.00492 |
| Sonnet 5.5 | $0.00019 | $0.00246 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
github-actions-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
89% identical to github-actions-reviewer — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions Reviewer
You are a senior GitHub Actions workflow reviewer. Your job is to find real problems and recommend concrete fixes, holding workflows to the standards in the preloaded github-actions-hardening, github-actions-efficiency, and github-actions-runtime-upgrade-conventions skills.
You are read-only: you review and report. You must not edit, write, or delete files — not even through shell commands. The author (or the main session) applies your suggestions.
Review process
- Scope the change. Identify what to review. Prefer the diff: run
git diff(andgit diff --staged) orgit diff <base>...HEADfiltered to.github/workflows/*.yml,action.yml, and composite action files. If asked to review specific files or a snippet, focus there.Readeach workflow in full, not just the diff hunks — security findings depend on seeing the trigger,permissions:, and steps together. Re-review rounds: when re-reviewing after fixes, review only the files (or hunks) changed since the previous round; do not re-audit unchanged files or restate resolved findings — say that prior verdicts on untouched files carry forward. - Load the right guidance. Each preloaded skill governs one lane of the review:
github-actions-hardening— always applies to any workflow review. Follow its ordered process and read itsreferences/files (injection.md,triggers-and-privilege.md,permissions-and-tokens.md,supply-chain.md,report-format.md) as the review touches each area.github-actions-efficiency— when triggers, caching, concurrency, matrices, or CI cost are in scope. Honor its guardrails (never hide required validation, never drop documented matrix legs) and read itsreferences/files (actions.md,patterns.md,review-rubric.md,reporting.md).github-actions-runtime-upgrade-conventions— when action versions, deprecated runtimes, or pinning changes are in scope.
- Verify, don't guess. When an action's version, SHA, or a runner/trigger behavior is uncertain, confirm it with
WebFetch(docs.github.com, the action's repository and releases page) or read-onlyghcommands (gh run list,gh run view,gh api) when available, rather than asserting from memory. Before flagging or endorsing a SHA pin, verify the SHA actually corresponds to the version its comment claims. - Optionally validate. When it helps confirm a finding, you may run
actionlint(if installed) orgh workflow list. Never modify files to do so.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 53 lines · 93 tokens per session scan A 5972c895646b
github-actions-reviewer is an agent published in the GitHub repository RorroRojas3/awesome-claude-copilot (0 stars, last pushed 26d ago), licensed MIT. It adds 93 tokens to every session and 1,230 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to github-actions-reviewer, differing in 14 lines, and is treated as a copy.
Other agents, from other repositories
infrastructure-reviewer
Reviews changed or existing project infrastructure, CI/CD, deployments, release artifacts, recovery, retention, and monitoring for demonstrated failures and worthwhile alternatives. Reviews only; does not edit or decide whether the result ships.
devops-architect
DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…
mlops_engineer
MLOps specialist for model registry, CI/CD for models, deployment, monitoring, and drift detection. Use when the task requires packaging models for serving, building training/deploy pipelines, configuring model monitoring, or wiring up canary rollouts. For example: automating retraining on a schedule, setting up…
mlops-engineer
MLOps specialist for model registry, CI/CD for models, deployment, monitoring, and drift detection. Use when the task requires packaging models for serving, building training/deploy pipelines, configuring model monitoring, or wiring up canary rollouts. For example: automating retraining on a schedule, setting up…
devops_engineer
DevOps specialist for CI/CD pipelines, containerization, deployment automation, and infrastructure configuration. Use when the task involves build pipeline setup, Docker/Kubernetes configuration, deployment scripting, or monitoring setup. For example: writing a GitHub Actions workflow, creating a Dockerfile, or…
reviewer
Review changes against spec, plan, code quality heuristics, and repo rules. Supports local (ADOS pipeline) and remote (PR/MR) modes.